{"id":"https://openalex.org/W2972494671","doi":"https://doi.org/10.21437/ssw.2019-11","title":"Generalization of Spectrum Differential based Direct Waveform Modification for Voice Conversion","display_name":"Generalization of Spectrum Differential based Direct Waveform Modification for Voice Conversion","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2972494671","doi":"https://doi.org/10.21437/ssw.2019-11","mag":"2972494671"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-11","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-11","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066130866","display_name":"Yuhuai Peng","orcid":"https://orcid.org/0000-0001-9343-5377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Huai Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101061014","display_name":"Hsin-Te Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsin-Te Hwang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7630717754364014},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7598192095756531},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6130691170692444},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5027499198913574},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46469637751579285},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4638652205467224},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4496508240699768},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4302121102809906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3539756238460541},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10635170340538025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630717754364014},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7598192095756531},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6130691170692444},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5027499198913574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46469637751579285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4638652205467224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4496508240699768},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4302121102809906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3539756238460541},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10635170340538025},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2019-11","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-11","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2883092465","https://openalex.org/W2348795485"],"abstract_inverted_index":{"We":[0,169],"present":[1],"a":[2,24,40,60,85,115,190,219,230],"modification":[3,11],"to":[4,28,75,91,159,175,189,206],"the":[5,37,57,65,69,88,95,110,125,133,141,147,152,166],"spectrum":[6],"differential":[7,67],"based":[8,119],"direct":[9],"waveform":[10,25,223],"for":[12],"voice":[13,29],"conversion":[14,30,102,154,196,209],"(DIFFVC)":[15],"so":[16],"that":[17,62,173,200,215],"it":[18,216],"can":[19,63,203,217],"be":[20,76,160,176,204],"directly":[21],"applied":[22],"as":[23],"generation":[26,224],"module":[27],"models.":[31],"The":[32],"recently":[33],"proposed":[34,187],"DIFFVC":[35,58,106,117],"avoids":[36],"use":[38],"of":[39,49,97,164,179],"vocoder,":[41],"meanwhile":[42],"preserves":[43],"rich":[44],"spectral":[45,66,149,153,167,195,208],"details":[46,172],"hence":[47],"capable":[48,163],"generating":[50],"high":[51],"quality":[52],"converted":[53,148],"voice.":[54],"To":[55],"apply":[56],"framework,":[59],"model":[61,90,155],"estimate":[64],"from":[68],"F0":[70,122,142],"transformed":[71,143],"input":[72,134],"speech":[73],"needs":[74],"trained":[77],"beforehand.":[78],"This":[79],"requirement":[80],"imposes":[81],"several":[82,171],"constraints,":[83],"including":[84],"limitation":[86],"on":[87,100,109,120,132,140],"estimation":[89],"parallel":[92],"training":[93,99],"and":[94,183,211],"need":[96,158,174],"extra":[98],"each":[101],"pair,":[103],"which":[104],"make":[105],"inflexible.":[107],"Based":[108],"above":[111],"motivations,":[112],"we":[113,198],"propose":[114],"new":[116],"framework":[118,202,221],"an":[121],"transformation":[123],"in":[124],"residual":[126,144],"domain.":[127],"By":[128],"performing":[129],"inverse":[130],"filtering":[131,139],"signal":[135,145],"followed":[136],"by":[137,184,229],"synthesis":[138],"using":[146],"features":[150],"directly,":[151],"does":[156],"not":[157],"retrained":[161],"or":[162],"predicting":[165],"differential.":[168],"describe":[170],"taken":[177],"care":[178],"under":[180],"this":[181,201],"modification,":[182],"applying":[185],"our":[186],"method":[188],"non-parallel,":[191],"variational":[192],"autoencoder":[193],"(VAE)-based":[194],"model,":[197,210],"demonstrate":[199],"generalized":[205],"any":[207],"experimental":[212],"evaluations":[213],"show":[214],"outperform":[218],"baseline":[220],"whose":[222],"process":[225],"is":[226],"carried":[227],"out":[228],"vocoder.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}